© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 140579
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è·¯
    -0.31
    迹
    -0.29
    SPORT
    -0.28
    chner
    -0.27
    ãĥ³ãĥĪ
    -0.27
    -sizing
    -0.27
    quier
    -0.26
    ChangedEventArgs
    -0.25
    å¶
    -0.25
    @stop
    -0.25
    POSITIVE LOGITS
    conf
    0.28
     succeeding
    0.26
    çļĦ帮åĬ©ä¸ĭ
    0.25
    大å¹ħ度
    0.25
     thi
    0.25
    cn
    0.24
     final
    0.24
    gar
    0.24
     mcc
    0.24
    èĻı
    0.24
    Activations Density 0.926%

    No Known Activations

    This feature has no known activations.